In the context of intelligent transportation systems (ITS), accurate thermal infrared image colorization plays a vital role in improving visual interpretation of traffic scenes, facilitating downstream analysis of vehicles and pedestrians under complex environmental conditions. Existing methods predominantly focus on point-wise correspondences, overlooking the spatial topology among neighboring pixels, which often leads to unrealistic and structurally inconsistent results. Moreover, most current methods employ small receptive fields that struggle to capture long-range dependencies and high-level semantics in complex infrared scenes. To address the above issue, we propose a Large Kernel convolution and Patch-wise Graph Contrastive Learning based generative adversarial network, called LKPG-GAN. Firstly, we introduce graph contrastive learning strategy to ensure topological consistency of color features and avoid unnecessary content deformation during the colorization process. Secondly, we propose Feature Selection Extraction Module extracts image features at the larger scale, enhancing the network’s ability to extract advanced features from thermal infrared images. Additionally, we design Feature Refinement Block within the network, which enables more effective extraction of color and structural features by the color infrared image generator network. Finally, we incorporate Attention Gate Module within the decoder, allowing operations on feature maps with a large receptive field to prevent information loss during the sampling process. Experimental evaluations on the KAIST dataset and the FLIR dataset prove that our proposed LKPG-GAN exceeds existing state-of-the-art methods in colorization performance. Furthermore, by focusing on typical urban traffic scenes contained in these datasets, our method establishes a solid foundation for further application and research in ITS thermal image processing, providing an effective tool for enhanced scene visualization and interpretation. Source code will be available athttps://github.com/cyanymore/LKPG-GAN

Building interpretation from remote sensing imagery primarily involves two fundamental tasks: building extraction and change detection. However, most existing methods address these tasks independently, overlooking their inherent correlation and failing to exploit shared feature representations for mutual enhancement. Furthermore, the diverse spectral, spatial, and scale characteristics of buildings pose additional challenges in jointly modeling spatial-spectral multi-scale features and effectively balancing precision and recall. The limited synergy between spatial and spectral representations often results in reduced detection accuracy and incomplete change localization. To address these challenges, we propose a Multi-Scale Spatial-Spectral Feature Cooperative Dual-Task Network (MSSFC-Net) for joint building extraction and change detection in remote sensing images. The framework integrates both tasks within a unified architecture, leveraging their complementary nature to simultaneously extract building and change features. Specifically, a Dual-branch Multi-scale Feature Extraction module (DMFE) with Spatial-Spectral Feature Collaboration (SSFC) is designed to enhance multi-scale representation learning, effectively capturing shallow texture details and deep semantic information, thus improving building extraction performance. For temporal feature aggregation, we introduce a Multi-scale Differential Fusion Module (MDFM) that explicitly models the interaction between differential and dual-temporal features. This module refines the network’s capability to detect large-area changes and subtle structural variations in buildings. Extensive experiments conducted on three benchmark datasets demonstrate that MSSFC-Net achieves superior performance in both building extraction and change detection tasks, effectively improving detection accuracy while maintaining completeness.

Infrared small target detection has recently benefftted greatly from deep neural models. However, existing frameworks generally ignore effective global information modeling, leading to poor detection when the target has high similarity to the background. We propose a dual-branch detection framework BFCD-Net, to address the above challenges through a clever combination of neural low-rank background modeling and multi-dimensional feature characterization. In neural low-rank background modeling. We adopt low-rank prior neural functions and neural regularization to effectively capture the global and local properties of the background. Specifically, the BFCD-Net framework contains a feature enhancement module, a distinguishing convolution kernel module, and a dynamic detector. The feature enhancement module improves network perception of targets by enlarging image resolution and enhancing the features of target. The distinguishing convolution kernel module enhances contrast between targets and backgrounds through adaptive feature segmentation and differential convolution operations. The dynamic detector optimizes feature representation and decision processes through adaptive weight learning. Additionally, we introduce an anti-wavelet transform fusion module to enhance multi-scale feature integration capabilities, and employs a three-dimensional total variation constraint to further improve the robustness of background modeling. Meanwhile, we propose a LGdicefunction. It improves the accuracy of the model in infrared small target detection tasks by explicitly focusing on the discrepancy between the predicted results and the real target. Experimental results demonstrate that BFCD-Net delivers superior detection performance across challenging datasets, especially on the NUDT-SIRST dataset, the IoU and Precision reach 84.55% and 94.99%. BFCD-Net provides an innovative solution for efficient and robust infrared small target detection.

Many rocks exhibit electrical anisotropic characteristics, leading to artifacts in isotropic inversion of dc resistivity data. To mitigate this issue, we employ the flexible unstructured finite element (FE) method for 3-D anisotropic forward modeling and anisotropic inversion for dc resistivity data. Synthetic inversions further validate algorithm feasibility. The code not only replicates the inversion of principal axis resistivities accomplished by previous researchers but also reconstructs challenging all angle parameters. Comparative analysis of inversion using isotropic and arbitrary anisotropic assumptions reveals that anisotropic inversion accurately recovers the parameters. Models comprising conductive and resistive targets, respectively, are utilized to stimulate two realistic scenarios. The angle parameters of conductive target are challenging to recover compared to a conductive one with the same anisotropy. We conduct comprehensive experiments to assess the results across various data types. Borehole-generated data enhances the principal resistivities resolution, aligning with the direction of the lines connecting to the boreholes, rather than all ones, whereas conventional surface configurations are unable to accurately capture discrepancies between principal resistivities and Euler angles. Moreover, the investigations confirm the resolvability of each anisotropy component, especially angle parameters, which depend on borehole distribution. These experiments on data-acquisition configurations greatly enhance the practical possibility of successfully collecting data containing anisotropy information, achieving reconstruction of angular parameters, and obtaining better images of principal axis resistivity in practical applications. Even with the correct anisotropic assumption, unreasonable data-acquisition configurations produce inversion results with distortion. Testing with the model containing multiple anisotropic targets further confirms the algorithm’s effectiveness.